蔡有城 (Youcheng Cai)

个人简介 (Biography)

蔡有城，男，现为中国科学技术大学数学科学学院博士后。主要研究领域为三维视觉、神经渲染、三维生成。近年来，在 SIGGRAPH、CVPR、TVCG 等一区国际期刊及 CCF-A 类会议上发表论文多篇。

教育与工作经历 (Education & Work Experience)

• 2023.9 - 至今：中国科学技术大学，数学科学学院，博士后
• 2018.9 - 2023.6：合肥工业大学，计算机科学与技术，博士
• 2014.9 - 2018.6：合肥工业大学，信息与计算科学，学士

发表论文 (Publications)

• 

  Mobile3DGS³: Accelerate Mobile 3DGS Rendering via Gradient-Aware Super-Sampling and Frame Interpolation

  Fan Gao, Yibo Zhao, Youcheng Cai*, and Ligang Liu

  Conditionally Accepted by SIGGRAPH 2026.

  [Coming Soon]
• 

  CraftMesh: High-Fidelity Generative Mesh Manipulation via Poisson Seamless Fusion

  Jincheng Hu, Yuxiao Wu, Youcheng Cai*, and Ligang Liu

  IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026

  [ArXiv] [Project]
• 

  Plug-and-Play PDE Optimization for 3D Gaussian Splatting: Toward High-Quality Rendering and Reconstruction

  Yifan Mo, Youcheng Cai*, and Ligang Liu

  IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026

  [ArXiv]
• 

  STAC: Plug-and-Play Spatio-Temporal Aware Cache Compression for Streaming 3D Reconstruction

  Runze Wang, Yuxuan Song, Youcheng Cai*, and Ligang Liu

  IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026

  [ArXiv] [Project] [Code]
• 

  AHC-NeRF: Autonomous, High-Quality Neural Reconstruction of Two-Layer Complex Nested Transparent Objects

  Youcheng Cai, Fan Gao, Yibo Zhao, Li Li*, and Ligang Liu

  IEEE Transactions on Visualization and Computer Graphics (TVCG), 2026

  [DOI]
• 

  Hash-NURF: Efficient Nested Transparent Object Reconstruction Using Multi-Resolution Hash Encoding

  Fan Gao, Yibo Zhao, Youcheng Cai*, and Ligang Liu

  The Visual Computer, 42(4): 1432-2315, 2026

  [DOI]
• 

  DragMV: Interactive Drag-Style Manipulation on Multi-View Images

  Junyan Qi, Youcheng Cai*, and Ligang Liu

  Computers & Graphics, 104344, 2025

  [DOI]
• 

  Importance Sampling Guided Neural Radiosity

  Huangsheng Du, Youcheng Cai*, Yutian Zhu, Peifeng Li, and Ligang Liu

  Computers & Graphics, 104472, 2025

  [DOI]
• 

  UANet: Uncertainty-Aware Cost Volume Aggregation-Based Multi-View Stereo for 3D Reconstruction

  Ping Lu, Youcheng Cai*, Jiale Yang, Dong Wang, and Tingting Wu

  The Visual Computer, 41(7): 4567-4580, 2025

  [DOI]
• 

  MV2MV: Multi-view Image Translation via View-Consistent Diffusion Models

  Youcheng Cai, Runshi Li, and Ligang Liu*

  ACM Transactions on Graphics (Proc. SIGGRAPH Asia), 43(6): 1-12, 2024

  [Project] [DOI]
• 

  HTMatch: An Efficient Hybrid Transformer Based Graph Neural Network for Local Feature Matching

  Youcheng Cai, Lin Li, Dong Wang, Xinjie Li, and Xiaoping Liu

  Signal Processing, 204: 108859, 2023

  [DOI]
• 

  MFNet: Multi-Level Fusion Aware Feature Pyramid Based Multi-View Stereo Network for 3D Reconstruction

  Youcheng Cai, Lin Li, Dong Wang, and Xiaoping Liu

  Applied Intelligence, 53(4): 4289-4301, 2023

  [DOI]
• 

  GlcMatch: Global and Local Constraints for Reliable Feature Matching

  Youcheng Cai, Lin Li, Dong Wang, Xintao Huang, and Xiaoping Liu

  The Visual Computer, 39(7): 2555-2570, 2023

  [DOI]